fix: Windows MSVC build errors in turboquant-kv-cache branch#37
Closed
YunagiHisa wants to merge 1 commit into
Closed
fix: Windows MSVC build errors in turboquant-kv-cache branch#37YunagiHisa wants to merge 1 commit into
YunagiHisa wants to merge 1 commit into
Conversation
- Add _USE_MATH_DEFINES for M_PI in ggml-turbo-quant.c (MSVC does not define it by default) - Fix DLL boundary issue for turbo3_cpu_wht_group_size via GGML_API setter function - Add TURBO_INNERQ_API export macros to turbo-innerq.cuh for Windows DLL compatibility - Include turbo-innerq.cuh directly in llama-kv-cache.cpp instead of raw extern declarations - Link ggml-cuda and define GGML_USE_CUDA for llama target when CUDA is enabled
Owner
|
Thank you @YunagiHisa for the Windows fixes and the dual-platform testing (RTX 4080 Super + RTX 3060). The setter function approach and direct include of turbo-innerq.cuh are clean solutions. These fixes are already included in PR #45 (weight compression branch) which carries the same set of Windows DLL visibility and M_PI fixes. Closing to avoid merge conflicts but your contribution and testing are appreciated. If you want to test weight compression on your 4080 Super, PR #45 has the full CUDA support: #45 |
hkmodd
pushed a commit
to hkmodd/llama-cpp-turboquant-triattention-buun-moelogging
that referenced
this pull request
May 20, 2026
cuda: tune Ada MMQ tile cap for small quants
fukuro-kun
pushed a commit
to fukuro-kun/fukuro-llama-cpp-turboquant
that referenced
this pull request
Jul 12, 2026
…026-07-12) 4 parallele Subagents (Vulkan/AMD, CUDA/MoE, arXiv, Multi-GPU/Batching) konsolidiert zu 25 neuen Items in ROADMAP: Tier 1 Quick Wins (3 neu): - AtomicBot-ai#31 K-Quant A-Matrix Transpose CM1 (PR ggml-org#22970, +5-15% PP auf Mars) - AtomicBot-ai#32 Pascal L1 Cache Tuning (-Xptxas -dlcm=ca, Styx) - TheTom#33 Per-Quant MMVQ/MMQ Batch Threshold (AMD MFMA, Mars/Venus) Tier 2 (7 neu): - TheTom#34 UBBoost, TheTom#35 Row-Packing DMMV, TheTom#36 Auto Param Fitting TP - TheTom#37 LFRU Expert Caching, TheTom#38 Conf-KV, TheTom#39 Talon, TheTom#40 MoE Load Balancing Tier 3 (5 neu): - TheTom#41 GRKV, TheTom#42 CapKV, TheTom#43 SliderQuant, TheTom#44 Alloc-MoE, TheTom#45 CUDA Streams QKV Tier 4 (10 neu): - TheTom#46-55: SpecMD, QUICK, FluxMoE, STAR-KV, VQKV, CompilerKV, SliceMoE, MoBiE, DASH-Q, GOOSE 7 PRs als bereits im Fork identifiziert (nicht erneut vorschlagen): ggml-org#21472, ggml-org#23764, ggml-org#22299, ggml-org#21611, ggml-org#22423, ggml-org#18749, Warp Shuffle, Constant Memory
fukuro-kun
pushed a commit
to fukuro-kun/fukuro-llama-cpp-turboquant
that referenced
this pull request
Jul 12, 2026
4 parallele Subagents evaluierten AtomicBot-ai#8, AtomicBot-ai#15, AtomicBot-ai#16, TheTom#34, TheTom#36, TheTom#37, TheTom#38, TheTom#40. Ergebnisse: AtomicBot-ai#16 ✅ bereits integriert, TheTom#38 ⏭️ verschoben, 6 ☐ offen. ROADMAP-Status für alle 8 Items mit Eval-Ergebnissen aktualisiert.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
Fix Windows MSVC build errors in the feature/turboquant-kv-cache branch.
This branch does not build on Windows due to several MSVC-specific issues.
Changes
_USE_MATH_DEFINESforM_PIinggml-turbo-quant.c(MSVC does not define it by default)turbo3_cpu_wht_group_sizeviaGGML_APIsetter functionTURBO_INNERQ_APIexport macros toturbo-innerq.cuhfor Windows DLL compatibilityturbo-innerq.cuhdirectly inllama-kv-cache.cppinstead of raw extern declarationsggml-cudaand defineGGML_USE_CUDAfor llama target when CUDA is enabledTest environment
AI usage disclosure
Diagnosed and fixed with assistance from Claude (Anthropic).
🤖 Generated with Claude